Overview and setup

Dataiku provides multiple AI Assistants to help users with various tasks across the Dataiku platform.

Some are entirely under customer control. They leverage LLM connections that you configure and control through LLM Mesh. Your code and metadata are not sent to Dataiku, but may be sent to third-party services according to the LLM you select.

Other assistants require an AI Server: either Dataiku’s cloud-based AI Services (automatically available), or your own AI Server hosted in DSS using your LLM connections through LLM Mesh.

Assistants using an AI Server

  • Flow Assistant allows users to use natural language to build data pipelines in the Flow.

  • SQL Assistant is a versatile SQL companion that allows you to generate, refine, and troubleshoot your SQL queries in SQL notebooks.

  • AI Search allows you to find and discover relevant data in the Data Catalog.

  • Generate Metadata automatically generates descriptions for your datasets and their columns. Since these descriptions are primarily based on sample values, we recommend enabling sample values to improve the accuracy and usefulness of the feature.

  • Stories AI allows you to generate presentations, slides, charts, and images inside Dataiku Stories.

  • AI Explain provides explanations for what your Flow or code does, allowing you to better understand and document your data pipelines and codebases.

  • Generate Steps allows users to use natural language to build steps in a Prepare recipe.

Using Dataiku’s AI Services

By default, these assistants use Dataiku’s own AI Server, hosted and managed by Dataiku.

They require that the Dataiku DSS server be connected to Internet, in order to talk to our AI Services.

Using the Dataiku AI Services is subject to acceptance of our Dataiku AI Services Terms of Use, which are linked from the “AI Assistants” page in Admin > Settings.

Once you have accepted the Terms of Use, you can turn on AI Services

Running your own locally-running AI Server, hosted by DSS

If you cannot use Dataiku’s AI Services, you also have the option of running your self the AI Server, hosted in your own DSS, and using your own LLM Mesh connections.

Please get in touch with your Dataiku Customer Representative to discuss access to this capability.

Assistants always under customer control

These assistants never go through Dataiku’s AI Services. They may either go through the LLM Mesh, or directly connect to 3rd-party services with whom you have agreements.

  • OpenAI Codex is a high-end coding agent, integrated in Code Studios

  • OpenCode is a full-featured open-source coding agent, integrated in Code Studios

  • GitHub Copilot is a powerful coding agent, integrated in Visual Studio Code in Code Studios

  • AI Code Assistant provides simple Python code generation and explanations in Jupyter Notebooks and in Visual Studio Code in Code Studios